Radar based tracking of slow moving objects

Abstract

An illustrative example method of classifying a detected object includes detecting an object, determining that an estimated velocity of the object is below a preselected threshold velocity requiring classification, determining a time during which the object has been detected, determining a first distance the object moves during the time determining a speed of the object from the first distance and the time, determining a second distance that a centroid of the detected object moves during the time, and classifying the detected object as a slow moving object or a stationary object based on a relationship between the first and second distances and a relationship between the estimated velocity and the speed.

What is claimed is: 
     
       1. A method of classifying a detected object, the method comprising:
 detecting an object; 
 determining that an estimated velocity of the object is below a preselected threshold velocity requiring classification; 
 assigning a bounding box to the object; 
 determining a time during which the object has been detected; 
 determining a first distance the object moves during the time; 
 determining a speed of the object from the first distance and the time; 
 determining a second distance that a centroid of the object moves during the time; 
 determining a value of a compensated range rate for moving detections inside the bounding box, and a ratio of the compensated range rate for moving detections inside the bounding box to a compensated range rate for moving detections outside the bounding box; and 
 classifying the object as a slow moving object or a stationary object based on a relationship between the first and second distances and a relationship between the estimated velocity and the speed. 
 
     
     
       2. The method of  claim 1 , wherein determining the speed of the object comprises using a Low Pass Filter. 
     
     
       3. The method of  claim 1 , wherein the determining the estimated velocity, time, and first distance comprises using a Kalman filter. 
     
     
       4. The method of  claim 1 , comprising:
 classifying the object as a slow moving object when the ratio exceeds a preselected threshold ratio. 
 
     
     
       5. The method of  claim 1 , comprising:
 determining whether a length and a width of the object are less than a preselected length and width. 
 
     
     
       6. The method of  claim 5 , comprising:
 determining whether a mean and standard deviation of compensated range rates of detections from the object are less than a preselected mean value and standard deviation value. 
 
     
     
       7. The method of  claim 6 , comprising:
 classifying the object as a slow moving or a stationary object based on the values of the length and width of the object and the mean and standard deviation of compensated range rates of detections. 
 
     
     
       8. The method of  claim 1 , comprising:
 assigning a bounding box to the object, wherein the bounding box has a preselected length and width. 
 
     
     
       9. A system for tracking a slow moving object, the system comprising:
 a tracking device configured to detect an object; and 
 a processor configured to:
 determine that an estimated velocity of the object is below a preselected threshold velocity requiring classification; 
 assign a bounding box to the object 
 determine a time during which the object has been detected; 
 determine a first distance the object moves during the time; 
 determine a speed of the object from the first distance and the time; 
 determine a second distance that a centroid of the object moves during the time; 
 determining a value of a compensated range rate for moving detections inside the bounding box, and a ratio of the compensated range rate for moving detections inside the bounding box to a compensated range rate for moving detections outside the bounding box; and 
 
 classify the object as a slow moving object or a stationary object based on a relationship between the first and second distances and a relationship between the estimated velocity and the speed. 
 
     
     
       10. The system of  claim 9 , comprising a Low Pass Filter configured to determine the speed of the object. 
     
     
       11. The system of  claim 9 , comprising a Kalman Filter configured to determine the estimated velocity, time, and first distance. 
     
     
       12. The system of  claim 9 , wherein the processor is configured to classify the object as a slow moving object when the ratio exceeds a preselected threshold ratio. 
     
     
       13. The system of  claim 9 , wherein the processor is configured to determine whether a length and a width of the object are less than a preselected length and width. 
     
     
       14. The system of  claim 13 , wherein the processor is configured to determine whether a mean and standard deviation of compensated range rates of detections from the detected object are less than a preselected mean value and standard deviation value. 
     
     
       15. The system of  claim 13 , wherein the processor is configured to classify the object as a slow moving or a stationary object based on the values of the length and width of the object and the mean and standard deviation of compensated range rates of detections. 
     
     
       16. The system of  claim 9 , wherein the processor is configured to assign a bounding box to the object, wherein the bounding box has a preselected length and width. 
     
     
       17. The system of  claim 9 , wherein the tracking device is on a vehicle. 
     
     
       18. The system of  claim 17 , wherein the vehicle is an autonomous vehicle.